100% processed locally, no cloud

From PDF or scan to usable data.

One API that extracts text, reads scans and validates the result. Runs entirely on our own servers: your documents stay yours.

PDF · Word · Excel · photos · email · XMLOCR in NL + ENREST + webhooks
0documents sent to third parties, by default
0file formats
0API call per document
0plans, freely configurable
How it works

Three steps, no fuss

No SDK and nothing to install on your side. Plain HTTP all the way.

1

Upload

Send a PDF or image to the API, or drop it into your dashboard.

2

Processing

Text extraction or OCR on our own machines, via a queue.

3

Result

Fetch JSON, text or a searchable PDF, or receive a webhook.

Features

Everything you want to do with documents

Everything you can do with documents, through the screen and through the API.

⚡

REST API

API-key access, limits per plan, OpenAPI description.

📄

Text extraction

Text and metadata from PDFs, per page, in reading order.

🔍

OCR for scans

Turn scans and photos into text and a searchable PDF.

🔔

Webhooks

A callback to your system as soon as a document is done.

⬇️

Export

Download the result as a searchable PDF.

▦

Tables

Detect tables and return them as rows and columns.

🏷️

Field extraction

Invoice number, amounts, dates and supplier, with validation of the result.

✂️

PDF editing

Split, merge, rotate, delete pages, compress, watermark and convert to images.

█

Redaction

Permanently black out personal data, addresses and bank details.

🔎

Search

Full-text search across all your documents.

Smart processing

Local first. AI only when needed.

DocuDex recognizes known documents itself, fast and private. Only what it is unsure about can go to an AI. That teaches your system something new, and after your approval DocuDex handles it itself next time.

⬆️ Upload PDF, photo, scan or Office file
⚡ Recognized locally Supplier, type and fields within seconds
🧠 Unsure? AI Your own local model or Claude, only if you enable it
✅ Checked IBAN, VAT sums and totals verified with fixed rules
📚 Keeps learning New recognition waits for your approval
🏠

Local model possible

Run a model on your own server or network (Ollama, LM Studio and others). Nothing leaves your environment.

🎛️

You choose

Local model, Claude or no AI. Off by default; the administrator enables it per user, and users can set up their own AI.

🔐

Always in control

With Claude, DocuDex asks permission per document. Every AI result stays flagged for review.

Formats

Almost everything you receive

From scans and photos to Office, email and e-invoices: it all goes through the same API.

PDF

PDF

Images and scans

PNGJPGGIFBMPTIFWEBPHEIC

Documents

DOCXXLSXPPTXODTODSODPEPUBRTF

Text and data

TXTMDLOGCSVTSVJSON

Web, email and e-invoices

HTMLXMLEML

XML is recognised as an e-invoice (UBL and CII), also when embedded in a PDF.

For developers

Connected in five minutes

One key, one endpoint, a predictable result. Examples in your own language.

{
  "id": "2420232f-cf3f-…",
  "status": "done",
  "pages": 3,
  "characters": 214,
  "pages_text": [
    { "page": 1,
      "text": "Notanummer 1234567890 …" }
  ],
  "warnings": []
}
Pricing

Honest plans

Pick the plan that fits. Change or cancel at any time.

Free

Try the service.
Free
  • 50 pages per month
  • Max. file size: 5 MB
  • API keys: 1
  • Retention (days): 7
  • REST API
  • Text extraction
  • OCR for scans
  • Webhooks
  • Export
  • Tables
  • Field extraction
  • PDF editing
  • Redaction
  • Search
Start for free
★ Popular

Basic

For small businesses and projects.
€ 19 / month
  • 1.000 pages per month
  • Max. file size: 25 MB
  • API keys: 3
  • Retention (days): 90
  • REST API
  • Text extraction
  • OCR for scans
  • Webhooks
  • Export
  • Tables
  • Field extraction
  • PDF editing
  • Redaction
  • Search
Request

Pro

For heavy use and integrations.
€ 79 / month
  • 10.000 pages per month
  • Max. file size: 100 MB
  • API keys: unlimited
  • Retention (days): 365
  • REST API
  • Text extraction
  • OCR for scans
  • Webhooks
  • Export
  • Tables
  • Field extraction
  • PDF editing
  • Redaction
  • Search
Request

Paid plans are activated manually after your request for now.

Prepaid

Prefer to pay per job?

Buy a bundle of credits and pay 1 credit per job. You get every feature of the Pro plan, no subscription.

Starter

100 credits
€ 19,00 · € 0,19 / credit
  • Every feature of the top plan
  • Credits do not expire
  • Failed on our side? Credits back
Get started
★ Best value

Plus

500 credits
€ 79,00 · € 0,16 / credit
  • Every feature of the top plan
  • Credits do not expire
  • Failed on our side? Credits back
Get started

Max

2000 credits
€ 249,00 · € 0,12 / credit
  • Every feature of the top plan
  • Credits do not expire
  • Failed on our side? Credits back
Get started
💶 Failed job? Credits back

If it goes wrong because of a fault on our side, you get your credits back right away. If a file truly cannot be recognized, or only produces unusable output, send it to us for inspection first. We look at it to improve our process and you get your credits back double.

Frequently asked questions


Where are my documents processed?

On our own servers. By default no external OCR or AI service sits in between; only if you choose AI reading with Claude does the content of that document go to Anthropic (you confirm that per document). Files are deleted automatically after your plan’s retention period, and you can delete them yourself through the API at any time.

Which files can I upload?

PDF, images (PNG, JPG, GIF, BMP, TIFF, WEBP, HEIC), Office (Word, Excel, PowerPoint and OpenDocument), EPUB, RTF, text files (TXT, MD, CSV, TSV, JSON, HTML, XML) and email (EML), including e-invoices (UBL/CII). The maximum file size depends on your plan.

How do I pay for BASIC or PRO?

Request the plan and we activate it after confirmation. Automatic payment follows later.

What if a job fails?

If it goes wrong because of a fault on our side, you get your credits back right away. If a file truly cannot be recognized, or only produces unusable output, send it to us for inspection using the button on that job. We look at it to improve our process and you get your credits back double. If the job succeeds but the result is different from what you hoped, no credits are returned.

What happens when I reach my limit?

The API answers with a clear error code (402 or 429). Your usage is always visible in your account and you can upgrade whenever you like.

Ready to process your first document?

Create a free account and use the API within a minute.

Start for free →